From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mta0.migadu.com (out-125.mta0.migadu.com [91.218.175.125]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EDCB93DB30C for ; Fri, 14 Aug 2026 03:30:24 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=91.218.175.125 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786678226; cv=none; b=uWI1bXx7f/MyfqTHBKRC+6R8bHG3SK0k7dOurOYgscz7Sy9xV7O/UrsPknw3MezKp2JI5Yqjw3NJzmKqWKPbiCb1/C80Q4fGeoxB7HmQXOqEQ38M1Wz/XEKym+80aqdBGe8mnMf9FeCtiuRCIaXSzDnZfSz8A2rr5yC5DR+6Yfs= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786678226; c=relaxed/simple; bh=BcGgUmgJ5bToxf4lyEoXBY/SvuxrW/zu7KIJo4jPTnU=; h=From:To:Cc:Subject:Date:Message-Id:MIME-Version; b=ri6qLDBoO75oHPAbIweCMPFxPEUQLmXQ5PdadFGehACKHrnP7/NNMIx/GuOhv0Y3jILCDGwkOB990O5VsHWfZZXs8HJvvDUKvT/bThFYFCTieCQekbvToKN4bVSTP9Tv56Z2L7fwY6ITVR8LM3nTX8YFCwSfmcM7gyRK/OCZlzM= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=oAPfvslq; arc=none smtp.client-ip=91.218.175.125 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="oAPfvslq" X-Envelope-To: linux-kernel@vger.kernel.org DKIM-Signature: a=rsa-sha256; bh=BcGgUmgJ5bToxf4lyEoXBY/SvuxrW/zu7KIJo4jPTnU=; c=simple/simple; d=linux.dev; h=from:to:subject:date:message-id:mime-version:content-type; s=key1; t=1786678222; v=1; x=1787283022; b=oAPfvslqk7lsFKqUtuWMXuZ3cDcQPOnHWUXVRVg9sGTEbh8rKM++3vcLQvCN4wCbvnKmnj7L 6drCx29caTeFSs+vCHjMHbl4u/XM9aJlb8JPHf+OQatlZDrwUfeD8PYHGSqfw30PdnzcmpCGY/u h0a2M3nouaVf2FztValnqbcE= X-Envelope-To: linux-kernel@vger.kernel.org Received: from mi-ThinkCentre-M760t.mioffice.cn (14.29.108.92) by smtp.migadu.com with ESMTPS id bae11645a998b6aa; Fri, 14 Aug 2026 03:30:22 +0000 X-Migadu-Flow: FLOW_OUT From: Ridong Chen To: Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Andrew Morton Cc: Muchun Song , David Finkel , Tejun Heo , cgroups@vger.kernel.org (open list:CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)), linux-mm@kvack.org (open list:CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)), linux-kernel@vger.kernel.org, Tao Cui , Ridong Chen , Ridong Chen Subject: [PATCH v4 0/2] mm, memcg: fix memory.peak reset clobbering other fds' watermark Date: Fri, 14 Aug 2026 11:30:03 +0800 Message-Id: <20260814033005.2481920-1-ridong.chen@linux.dev> X-Mailer: git-send-email 2.34.1 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit From: Ridong Chen The memory.peak / memory.swap.peak per-fd watermark tracking has two issues. Each open fd is a watcher and reads back max(its own value, the shared local_watermark); both bugs live in that scheme. Worst case for both is the same and is userspace-visible: a reader of memory.peak (or memory.swap.peak) gets a value lower than the true peak, so a tool that sizes or bills a cgroup by its peak usage under-reports it. Patch 1 (read side) fixes the race Sashiko pointed out in the v1 review [1]: peak_show() inspects local_watermark and the per-fd values without holding peaks_lock, so a reader that races an unrelated peak_write() reset briefly observes the lowered value. Transient. It takes peaks_lock in the show path. Patch 2 (write side) fixes peak_write(): on a reset it stores the current usage into the other watchers instead of the old watermark, so once usage has dropped from a peak a reset on one fd drags every other fd's peak down too, even fds that never reset. --- Changes since v3: - Switch to guard(spinlock) in the peak readers, suggested by Muchun. Changes since v2: - Spell out the worst-case userspace-visible effect, per Andrew's Go back to v1 [2]. Changes since v1: - New patch 1: hold peaks_lock in the peak readers (Sashiko). - Patch 2: floor the peers with max(usage, local_watermark), mirroring peak_show(), and skip the writing fd (Johannes Weiner). [1] https://sashiko.dev/#/patchset/20260730115314.1069089-1-ridong.chen@linux.dev?part=1 [2] https://lore.kernel.org/all/20260730115314.1069089-1-ridong.chen@linux.dev/ Ridong Chen (2): memcg: acquire peaks_lock when reading memory.peak mm, memcg: fix memory.peak reset clobbering other fds' watermark mm/memcontrol.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) -- 2.34.1